# Trust, Then Verify: Auditing Every AI Change in Ads

Google's change history plus a connector-side audit trail gives you two independent ledgers of what the AI did. Reconcile them weekly.

Blog · Published 2026-08-10, updated 2026-10-03.

> Auditing AI changes in Google Ads rests on two independent ledgers. Google's change history records what changed in the account — entity, old and new values, source, user — for the past two years. The connector's audit trail records what the AI was asked to do — tool, account, success or refusal, reason, timestamp. Reconcile them weekly: every account change should trace to a successful call, and every refused call should have no account effect. When both hold, trust stops being a feeling.

Your agent builds campaigns, shifts budgets, and adds keywords at the speed
of a sentence — expert moves, made in seconds. Which is exactly why the
question every stakeholder eventually asks about AI in an ad account is
some version of "how do I know what it actually did?" The answer should
never be "ask the AI" — a system reporting on itself is testimony, not
evidence. The real answer is that you hold two independent written records,
made by different parties, and they must agree. Google keeps one. The
connector keeps the other. Reconciling them is a ten-minute weekly habit.

## Two ledgers, kept by different hands

Google's [change history](https://adcopilot.cloud/glossary/change-history) is the account's own
diary: every material change for the past two years, with the entity, the
before and after values, the date, the source and the user who made it. It
is kept by Google, on Google's side, and no tool that talks to the account
can edit it.

The connector's [audit trail](https://adcopilot.cloud/glossary/audit-trail) is the AI-side record:
every call the agent made — tool, target account, success or refusal, the
reason, the timestamp. It is kept by the connector, outside the account,
and captures things Google never sees, including the calls that were
*refused* before they reached Google at all.

Independence is the point. Either record alone can be doubted in principle;
in agreement, they corroborate. This is the boring, load-bearing machinery
behind the word [trust in an AI-connected account](https://adcopilot.cloud/security).

## What each ledger records — and what neither can

| Question | Change history | Audit trail |
| --- | --- | --- |
| What changed, old and new values | Yes | Only what was requested |
| Who made it | Google user identity | Connector seat and tool call |
| Attempted but refused actions | No — they never happened | Yes, with the refusal reason |
| Reads (queries, reports) | No | Yes |
| Changes from other tools and humans | Yes | No |
| Retention | Two years | 180 days on AdCopilot |

Read the gaps as instructions. Only the audit trail shows refusals and
reads, so connector-side logging is your record of what the AI *tried* and
*saw*. Only change history shows what humans, scripts and auto-apply did,
so it is your record of everything-else. And neither ledger records *why* —
the reasoning lives in the AI conversation and in your own decision notes,
which is why the weekly review ends by writing two sentences of judgement
down.

The retention row carries a quiet obligation. Google's two-year window
outlives most reporting questions but not all accountability ones — client
disputes, handovers and annual reviews regularly reach past the horizon of
whatever surface holds the record, and the connector trail is the shorter
of the two: AdCopilot deletes its entries after 180 days. Make your own
decision log the permanent record, copy into it the connector entries that
back each decision when you reconcile, and export from Google's side
anything you can imagine needing to defend twice.

## The weekly reconciliation prompt

Bring the connector's record with you — the audit trail lives on the
connector's side, not behind a tool the agent can call, so copy the
week's entries into the conversation. Then one prompt does the
mechanical half of the audit:

> Here is my connector audit trail for the last 7 days: every write call,
> with account, tool, outcome and timestamp. Pull change history for the
> same window. Match them: list account changes with no corresponding
> successful call, refused or failed calls, and successful calls whose change I
> should verify landed as intended. Table, newest first.

Three lists come back, and each has one correct response. **Unmatched
account changes** — identify the other actor (a teammate, a script,
auto-apply). **Refusals** — read the reasons; a refusal pattern is either
the system working or a prompt that keeps asking for the wrong thing.
**Successful-but-unverified** — spot-check the two or three that touched
spend. Most weeks all three lists are short, which is exactly what makes
the ritual sustainable.

## Attribution when five people share a roster

Reconciliation collapses if every change says "the AI did it". The fix is
structural: per-member connectors. Each teammate connects under their own
Google sign-in, so a change lands in Google's change history under that
person's identity, and in the audit trail under that person's seat. When
[several people run AI across shared accounts](https://adcopilot.cloud/blog/human-in-the-loop-ppc),
"whose sign-in made this budget change" has a name in both ledgers — and any
seat can be narrowed or revoked without touching the rest. A shared
service-account connector produces the opposite: perfect logs of an
anonymous crowd.

## Investigating a surprise: anomaly to answer in minutes

The audit muscle exists for the day a chart jumps. A concrete shape of
the day: Tuesday's spend on a lead-gen campaign runs well above its
recent range. The anxious version of what follows is a group chat asking
"did anyone touch this?" The audited version: change history shows a
budget increase Monday evening attributed to a named teammate's Google
identity; the audit trail shows the matching successful call from that
teammate's connector seat; the conversation attached to it argues the
campaign was pacing under target with the month's evidence laid out. Five
minutes in, the question has changed from *who did this* to *was the
argument right* — which is the question that was always worth the
meeting.

The walk is always the same four steps, and — with the trail alongside it
— the agent can run them in one conversation:

1. **Time-box the anomaly.** "CPA doubled on Tuesday" — get the hour range
   from the metrics, not from memory.
2. **Pull both ledgers for the window.** Change history first: what changed
   in or just before the window, with old and new values.
3. **Match to the trail.** If the change was AI-made, the trail shows the
   call, and the conversation shows the argument for it. The trail cannot
   show whether anyone approved the call: that prompt is your AI client's,
   not the connector's.
4. **Judge the argument, not just the outcome.** A justified change that
   aged badly is a revert. An unjustified one is a process fix: tighten the
   tier, the prompt or the approver.

Without the two ledgers this investigation is a meeting. With them it is
ten minutes, and it usually ends in the least dramatic sentence in PPC:
"found it, reverted, noted."

## What a clean month of logs earns you

The reconciliation habit has a compounding payoff beyond catching problems:
it generates the evidence that justifies loosening the reins. A month where
every change matched a successful call, refusals were sensible, and no
change you allowed turned into a regret is not just reassurance — it is data about
which action classes your review adds nothing to. That is the rational
trigger for widening autonomy one tier at a time, with the same ledgers
watching the wider scope.

Trust in an AI system, done properly, is not a leap anyone takes. It is a
balance that two ledgers keep — and hand you, reconciled, every Friday.
[Start free](https://app.adcopilot.cloud/signup) and run your first
reconciliation prompt this week.

## Questions

### Does Google's change history show API changes?

Yes. Changes made through the Google Ads API appear in change history alongside interface changes, attributed to the authenticated user that made them. Because a well-designed connector runs under your own Google sign-in rather than a shared service account, AI-made changes surface under the identity of the teammate whose connector executed them — which is exactly what makes cross-team attribution possible.

### How long is Google Ads change history retained?

Two years. Google's change history lists changes to the account, campaigns and ad groups from the past two years; anything older is unavailable in that surface. That window is generous for weekly reconciliation but finite for institutional memory. A connector's audit trail is shorter still — AdCopilot deletes its entries after 180 days — so your own decision log is the record you control: summarise into it anything you may need to defend later than that.

### What if I find a change with no matching connector call?

Then a human, a script, an auto-applied recommendation or another tool made it — which is precisely the kind of fact the reconciliation exists to surface. Check the change history's source and user fields first: auto-applied recommendations and Google Ads scripts identify themselves. An unattributable change in a multi-tool account is an access-hygiene finding, and worth resolving before it repeats.

---

This is the markdown copy of https://adcopilot.cloud/blog/verify-what-your-ai-changed. The index of the site's pages is https://adcopilot.cloud/llms.txt.
